Architecture · 2024–now · AI Present
Context / tool protocols
Standard ways for models to talk to tools and data — MCP after the 2026 stateless rewrite, not one-off plugin snowflakes.
Why Context / tool protocols stuck
Context protocols stuck because every vendor reinventing tool schemas is how integration hell returns. The 2026 spec made MCP ordinary HTTP — no sticky sessions — and LangChain, Compose, and OpenAI Agents treated it as plumbing. They will fail if treated as magic product differentiation. The durable win is boring interoperability; the fad is protocol as keynote adjective.
Compare with
Related
Framework · 2023–now
LLM orchestration frameworks
Chains, tools, memory, and agents as a framework — LangChain-class glue sold as architecture. Fatigue was real; the repos became MCP clients, not tombstones.
$ Teams adopted chain/agent frameworks before they had a single reliable tool call. Abstraction layers multiplied while prompt quality stayed flat.
Practice · 2023–now
Agent ops / LLM observability
Tracing, cost caps, and prompt versioning for production LLM features — mostly constrained tool loops, not autonomous agents. Datadog for tokens.
Framework · 2023–now
LLM app frameworks
LangChain-class glue mutated into MCP clients and thin wrappers around vendor APIs. The durable pieces are still boring: evals, retrieval, and product UX.
Platform · 2025–now
Vendor agent APIs
The Codex/Claude loop as a product SKU — durable sessions, compaction, subagents, and a sandbox you do not own.
$ Teams replaced a weekend of LangGraph glue with a managed session API, then discovered residency, recovery, and kill switches all live on the vendor side of the harness.
Practice · 2025–now
Agent skills / SKILL.md
Packaged workflows in a folder — name, description, scripts — loaded on demand instead of stuffing the system prompt.